Wang, R., Falk, J. I. T., Pontil, M., & Ciliberto, C. (2024). Robust Meta-Representation Learning via Global Label Inference and Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(4), 1996–2010. https://doi.org/10.1109/tpami.2023.3328184
Abstract:
Few-shot learning (FSL) is a central problem in meta-learning, where learners must efficiently learn from few labeled examples. Within FSL, feature pre-training has become a popular strategy to significantly improve generalization performance. However, the contribution of pre-training to generalization performance is often overlooked and understudied, with limited theoretical understanding. Further, pre-training requires a consistent set of global labels shared across training tasks, which may be unavailable in practice. In this work, we address the above issues by first showing the connection between pre-training and meta-learning. We discuss why pre-training yields more robust meta-representation and connect the theoretical analysis to existing works and empirical results. Secondly, we introduce Meta Label Learning (MeLa), a novel meta-learning algorithm that learns task relations by inferring global labels across tasks. This allows us to exploit pre-training for FSL even when global labels are unavailable or ill-defined. Lastly, we introduce an augmented pre-training procedure that further improves the learned meta-representation. Empirically, MeLa outperforms existing methods across a diverse range of benchmarks, in particular under a more challenging setting where the number of training tasks is limited and labels are task-specific.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the A*STAR - Career Development Fund
Grant Reference no. : C210812045